Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 123145
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    approval
    -0.06
    }`)↵
    -0.06
     Turns
    -0.06
    .can
    -0.06
     pies
    -0.06
     STORE
    -0.06
     cost
    -0.06
    aac
    -0.06
    initial
    -0.06
     Cic
    -0.06
    POSITIVE LOGITS
    (rad
    0.07
     kort
    0.06
     Totally
    0.06
    ForKey
    0.06
    �
    0.06
     stanov
    0.06
     двад
    0.06
    客
    0.06
    .groups
    0.06
    .frame
    0.06
    Activations Density 0.018%

    No Known Activations